سامانه همایش‌ها TSTA | ثبت‌نام و ارسال مقاله کنفرانس‌ها و کنگره‌های ملی

صفحه اصلی / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

Multi-Objective Optimization of the Impeller of a mini Blood Pump: Balancing Outlet Pressure and Scalar Shear Stress

نویسندگان :

Reza Sahebi-Kuzeh kanan¹ Hanieh Niroomand-oscuii² Habib Badri Ghavifekr³ Farzan Ghalichi⁴

1- Tabriz University of Technology 2- Tabriz University of Technology 3- Tabriz University of Technology 4- Tabriz University of Technology

کلمات کلیدی :

Blood pump،Computational fluid dynamics،Optimization،Response Surface Methodology،Multi-Objective Genetic Algorithm

چکیده :

Cardiovascular diseases are among the leading causes of mortality worldwide, and blood pumps and ventricular assist devices play a key role in advanced care. To overcome limitations of prior studies, namely the small number of geometric parameters and single objective optimization, we present a hybrid framework that integrates response surface methodology, a neural network surrogate, and a multi objective genetic algorithm to design the impeller of a small blood pump at a specified operating point. Fifteen geometric parameters were varied and 290 computational simulations were performed to construct the database and train the surrogate. The optimization objectives were to maximize outlet pressure and to keep the mean scalar shear stress at 50 Pa.Compared with the baseline impeller, the optimized design achieved a 6–7% increase in outlet pressure and about a 15% increase in static head, while the mean wall shear stress decreased by about 17% and the hemolysis index dropped by nearly 50%. The optimized blade reduced high-shear stress near the leading edge, yielded a more uniform shear field, and exhibited smoother pressure growth and weaker jet–wake structures, indicating more uniform blade loading, better pressure recovery, and lower mixing losses. The neural network correctly captured the improvement trends but showed a modest discrepancy: it overestimated outlet pressure by about 13% and underestimated the shear-stress reduction by about 19% relative to simulation-verified values. Overall, the proposed framework simultaneously improves hydraulic performance and hemocompatibility and offers a practical route for multi-objective optimization of small blood-pump impellers.

لیست مقالات

لیست مقالات بایگانی شده

بهبود امنیت داده در رایانش ابری عمومی با استفاده از یک معماری ترکیبی مبتنی بر AES و ECC

فاطمه رمضانی - علیرضا چمکوری

A Real-Time Integrated Framework for Face Detection, Gender, and Emotion Recognition Using Convolutional Neural Networks

Mostafa Asgarinejad - Elias Ebrahimzadeh - Vida Mirabolfathi - Lila Rajabion - Hamid Soltanian-Zadeh

بررسی کاربرد و چالش های هوش مصنوعی در مدیریت لجستیک بنادر

ایمان حق شناس - دامون رزمجویی

Graph Convolutional Network–Based Surrogate Modeling for MRI-EEG Connectivity Analysis

Arshia Rezaei - Bahareh Abbaszadeh

Deep Learning Approaches for Alzheimer’s Disease Diagnosis: A Comprehensive Review

Mahdi Jafari Asl - Saba Haji Molla Rabie

چالش‌های اخلاقی هوش مصنوعی در حسابداری مدیریت

محمدرضا پورعلی لاکلایه - مصطفی لطفی

تشخیص حملات اینترنتی با مدل های زبانی بزرگ تقطیری در شبکه های توزیع شده

جواد جهانگیری درزه کنانی - امین بابازاده

TransFuse++: A Hybrid CNN-Transformer Architecture with Cross-Attention, Temporal Modeling, and Uncertainty Estimation for Medical Image Segmentation

Masoud Noroozi - Sayna Jamaati - Hamed Aghapanah - Ali Saeeidi Rad - Mahsa Asadi Anar - Ali Darzi - Mahla Shokouhfar - Helia Sadat Kazemi - Mohammadreza Ghahari - Mohammad Saeed Soleimani Meigoli - Jafar Majidpour - Hossein Arabi - Ali Reza Karimian

تاثیر ویژگی‌های حسابرس مستقل بر ارزش افزوده اقتصادی با تاکید بر اثربخشی هیئت مدیره در صنعت فولاد

فرناز علی بالازاده یامچلو - رامین علی بالازاده یامچلو

تاثیر رویکرد هوش مصنوعی بر صنعت گردشگری جوامع مختلف ایرانی

حسین بوذری

بیشتر